io.github.SanZiNEO/veddata is an MCP server that MCP server for AI agents: discover a web page's data sources and drive the page to reach them. Its tool list has not been published yet over stdio, requires no API key, and scores 57/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients - only the file and path differ.
{
"mcpServers": {
"veddata": {
"args": [
"veddata",
"--response-dir",
"E:\\path\\to\\out"
],
"command": "uvx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
MCP server for AI agents: discover a web page's data sources and drive the page to reach them.
Run this in your terminal to verify the server starts. Then let us know if it worked - your result helps other developers.
uvx 'veddata' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories - click any category to see the underlying evidence.
No known CVEs.
Checked veddata against OSV.dev.
Be the first to review
Have you used this server?
Share your experience - it helps other developers decide.
Sign in to write a review.
Others in browser / data
Token-efficient database MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, SQLite
Manage Supabase projects — databases, auth, storage, and edge functions
Open-source web scraper for AI agents with scrape, crawl, and map tools
A cross-platform desktop application for managing AI Agents and MCP Servers. 一款用于管理AI智能体与MCP服务器的跨平台桌面应用程序。
MCP Security Weekly
Get CVE alerts and security updates for io.github.SanZiNEO/veddata and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
一个模型上下文协议(MCP)服务器:在网页上做数据源发现 —— 捕获网络请求、提取内嵌数据、分析脚本,并通过交互与监测点跟踪数据流向。
<script> 标签里的 JSON 与 window 全局变量css=、//(XPath)选择器定位一次性运行(无需安装,推荐):
{
"mcpServers": {
"veddata": {
"command": "uvx",
"args": ["veddata", "--response-dir", "E:\\path\\to\\out"]
}
}
}
或先安装再使用:uv tool install veddata(或 pip install veddata),然后
{
"mcpServers": {
"veddata": {
"command": "veddata",
"args": ["--response-dir", "E:\\path\\to\\out"]
}
}
}
从源码运行(开发用):
uv venv
uv pip install -e ".[dev]"
客户端配置(标准输入输出):
{
"mcpServers": {
"veddata": {
"command": "E:\\path\\to\\veddata\\.venv\\Scripts\\python.exe",
"args": ["-m", "veddata.server",
"--profile-dir", "E:\\path\\to\\profile",
"--response-dir", "E:\\path\\to\\out"]
}
}
}
| 参数 | 说明 |
|---|---|
--profile-dir <目录> | 浏览器配置目录(持久化,保留登录状态)。默认 <用户数据根>/veddata/profile |
--response-dir <目录> | ved_export、ved_screenshot 的落盘目录。未配置时这两个工具在写盘时报错 |
| 环境变量 | 说明 |
|---|---|
HEADLESS=true | 无窗口模式(默认为有窗口) |
BROWSER_PATH <路径> | 指定浏览器可执行文件(填 edge 表示使用 Edge) |
BROWSER_ADDRESS <地址> | 接管已在运行的浏览器(调试协议地址),而不是自行启动 |
tab="A,B" 或 tabs=["A","B"],最后一个标签不会被关掉<symbol>、<defs>、<path> 等)filter="sessionid,sid_tt" 只取指定的几个(命中时值不裁剪,用来取完整票据)input、click、select、scroll;可单步或链式;target 支持可见文本、css= 或 //;定位只查询不点击(探测不产生副作用),未命中会给出最接近的可见文本;页面自跳后用 force=true 免去手动 ved_statusparams / headers 里传 null 表示删除该键;默认从浏览器同步 cookie(你显式给的 cookie 头优先);raw=true 是「原样发出」——不继承捕获记录的头/参数、不注入 cookie 与 XSRF,只发你给的东西。返回里回显实际发出的请求(最终 URL、每个请求头的来源、被删除 / 未发送的键),据此判断「哪些东西是必需的」ved_apis、ved_inspect、ved_watch(collect) 等按需获取。ved_status、ved_tabs 会重新建立观测。ved_close 关闭;通过 BROWSER_ADDRESS 接管的仅断开连接。以 svgrepo 为例(该站点没有公开接口文档,AI 只能自己侦察)。一条工具链跑完:
[
{"tool": "ved_open"},
{"tool": "ved_goto", "args": {"url": "https://www.svgrepo.com/vectors/arrow/"}},
{"tool": "ved_goto", "args": {"url": "https://www.svgrepo.com/svg/535197/a
... [View full README on GitHub](https://github.com/sanzineo/veddata#readme)